SIGCSE Virtual 2024
Thu 5 - Sun 8 December 2024
Sat 7 Dec 2024 16:30 - 17:00 at Track 1 - Papers 3: AI (2)

There is a growing interest in utilizing large language models (LLMs) for various educational applications. Recent studies have focused on the use of LLMs for generating various educational artifacts for programming education, such as programming exercises, model solutions or multiple-choice questions (MCQs). The ability to efficiently and reliably assess the quality of such artifacts has become of paramount importance. In this paper, we investigate an example use case of assessing the quality of programming MCQs. To that end we carefully curated a data set of 192 MCQs annotated with quality scores based on a rubric that assesses crucial aspects such as clarity, the presence of a single correct answer, the quality of distractors, and alignment with learning objectives (LOs). Our results show that the task presents a considerable challenge even to the state-of-the-art LLMs. To further research in this important area we release the data set as well as the evaluation pipeline to the public.

Sat 7 Dec

Displayed time zone: (UTC) Coordinated Universal Time change

16:30 - 18:00
Papers 3: AI (2)Conference at Track 1
16:30
30m
Paper
A Benchmark for Testing the Capabilities of LLMs in Assessing the Quality of Multiple-choice Questions in Introductory Programming Education
Conference
Aninditha Ramesh Carnegie Mellon University, Arav Agarwal Carnegie Mellon University, Jacob Doughty Carnegie Mellon University, Ketan Ramaneti Carnegie Mellon University, Jaromir Savelka Carnegie Mellon University, Majd Sakr Carnegie Mellon University
17:00
30m
Paper
Examining the Relationship between Socioeconomic Status and Beliefs about Large Language Models in an Undergraduate Programming Course
Conference
Amy Pang University of Michigan, Aadarsh Padiyath University of Michigan - Ann Arbor, Diego Viramontes Vargas University of Michigan, Barbara Ericson University of Michigan
17:30
30m
Paper
Generative AI in Introductory Programming Instruction: Examining the Assistance Dilemma with LLM-Based Code Generators
Conference
Eric Poitras Dalhousie University, Brent Crane Dalhousie University, Angela Siegel Dalhousie University